INDEX

Explanations

technical terminology related to data management and analysis

oai_token-act-pair · gpt-4o-mini Triggered by @bot

after prepositions or conjunctions

np_acts-logits-general · gemini-2.0-flash

data reconstruction and tracking

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wikimedijinoj

-0.40

VAS

-0.39

 knit

-0.39

triangleq

-0.37

icon

-0.36

 Vitro

-0.35

ุก

-0.35

mtx

-0.35

oa̍t

-0.35

POSITIVE LOGITS

GEBURTSDATUM

0.59

 وتسجيلات

0.56

twimg

0.54

 '\\;'

0.52

ItemBackground

0.49

Біографія

0.47

InputBorder

0.47

PhysRevD

0.46

 ROOT

0.45

(!__

0.43

Activations Density 0.554%

technical terminology related to data management and analysis

after prepositions or conjunctions

data reconstruction and tracking

No Comments

No Known Activations